Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 6132 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3328. Min Range: -2.3328

Max Act: 2.3328. Min Act: -0.0000

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.9078. Min Act: -0.0000

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.7729. Min Act: -0.0000

Data Index: 219053 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.8473. Min Act: -0.0000

Data Index: 769365 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.8514. Min Act: -0.0000

Data Index: 494562 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.6803. Min Act: -0.0000

Data Index: 1655961 (Python Code)

Max Activating Token Index: 962

Text #6

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1010002 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.6115. Min Act: -0.0000

Data Index: 423867 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.5519. Min Act: -0.0000

Data Index: 1222029 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.5665. Min Act: -0.0000

Data Index: 1037481 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.6296. Min Act: -0.0000

Data Index: 1050584 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.5480. Min Act: -0.0000

Data Index: 1243373 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.5010. Min Act: -0.0000

Data Index: 453330 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.4117. Min Act: -0.0000

Data Index: 73546 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.3212. Min Act: -0.0000

Data Index: 780284 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.3889. Min Act: -0.0000

Data Index: 74621 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.4402. Min Act: -0.0000

Data Index: 898620 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1250953 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.5040. Min Act: -0.0000

Data Index: 1218232 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 2.3328. Min Range: -2.3328

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1127536 (C4 (Web Text))

Max Activating Token Index: 334